poca-SoccerTwos / run_logs /timers.json
MarshallPF's picture
Overnight Train
515da65
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.7279229164123535,
"min": 1.7279229164123535,
"max": 3.289775848388672,
"count": 133
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 258939.609375,
"min": 258939.609375,
"max": 552787.625,
"count": 133
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 61.237541528239205,
"min": 48.09305373525557,
"max": 814.3695652173913,
"count": 133
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 147460.0,
"min": 146264.0,
"max": 152888.0,
"count": 133
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1639.2915307065407,
"min": 1196.5289883887622,
"max": 1646.544195586087,
"count": 133
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 1973707.002970675,
"min": 38436.91673612366,
"max": 2346348.54834277,
"count": 133
},
"SoccerTwos.Step.mean": {
"value": 9974934.0,
"min": 74588.0,
"max": 9974934.0,
"count": 133
},
"SoccerTwos.Step.sum": {
"value": 9974934.0,
"min": 74588.0,
"max": 9974934.0,
"count": 133
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.03339169919490814,
"min": -0.07884147018194199,
"max": 0.1675855964422226,
"count": 133
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -40.20360565185547,
"min": -82.94122314453125,
"max": 213.3364715576172,
"count": 133
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.033170223236083984,
"min": -0.07947618514299393,
"max": 0.16903914511203766,
"count": 133
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -39.936946868896484,
"min": -83.60894775390625,
"max": 215.18682861328125,
"count": 133
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 133
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 133
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.060725912550755115,
"min": -0.2684082464151776,
"max": 0.26833244233457293,
"count": 133
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -73.11399871110916,
"min": -150.45839977264404,
"max": 341.5871990919113,
"count": 133
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.060725912550755115,
"min": -0.2684082464151776,
"max": 0.26833244233457293,
"count": 133
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -73.11399871110916,
"min": -150.45839977264404,
"max": 341.5871990919113,
"count": 133
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.017163605819930833,
"min": 0.013692020925009275,
"max": 0.01980743935710052,
"count": 133
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.0514908174597925,
"min": 0.043616841247179156,
"max": 0.07922975742840208,
"count": 133
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.1028438894285096,
"min": 0.0019397098630886628,
"max": 0.10635385991384586,
"count": 133
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.3085316682855288,
"min": 0.005819129589265989,
"max": 0.4254154396553834,
"count": 133
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.1049139609767331,
"min": 0.001940577875292446,
"max": 0.10770234552522501,
"count": 133
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.3147418829301993,
"min": 0.005821733625877338,
"max": 0.43080938210090003,
"count": 133
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 133
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0009,
"min": 0.0009,
"max": 0.0012,
"count": 133
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 133
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.6000000000000002,
"min": 0.6000000000000002,
"max": 0.8000000000000003,
"count": 133
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 133
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.015000000000000003,
"min": 0.015000000000000003,
"max": 0.020000000000000004,
"count": 133
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 133
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 133
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1682625164",
"python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/marshallpostle-floyd/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1682662874"
},
"total": 37709.464511965,
"count": 1,
"self": 1.9224007529992377,
"children": {
"run_training.setup": {
"total": 0.021891391000000038,
"count": 1,
"self": 0.021891391000000038
},
"TrainerController.start_learning": {
"total": 37707.520219821,
"count": 1,
"self": 14.835836596554145,
"children": {
"TrainerController._reset_env": {
"total": 2.6730574149865314,
"count": 25,
"self": 2.6730574149865314
},
"TrainerController.advance": {
"total": 37689.864224052464,
"count": 675837,
"self": 16.304659055022057,
"children": {
"env_step": {
"total": 10391.698108468974,
"count": 675837,
"self": 8556.412238605564,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1825.7696385712222,
"count": 675837,
"self": 81.48673259642987,
"children": {
"TorchPolicy.evaluate": {
"total": 1744.2829059747924,
"count": 1255662,
"self": 1744.2829059747924
}
}
},
"workers": {
"total": 9.516231292187717,
"count": 675837,
"self": 0.0,
"children": {
"worker_root": {
"total": 37679.335423007506,
"count": 675837,
"is_parallel": true,
"self": 30778.31575545263,
"children": {
"steps_from_proto": {
"total": 0.04989411099655472,
"count": 50,
"is_parallel": true,
"self": 0.01035485201326325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.03953925898329147,
"count": 200,
"is_parallel": true,
"self": 0.03953925898329147
}
}
},
"UnityEnvironment.step": {
"total": 6900.969773443879,
"count": 675837,
"is_parallel": true,
"self": 368.5233629400491,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 231.55350674922573,
"count": 675837,
"is_parallel": true,
"self": 231.55350674922573
},
"communicator.exchange": {
"total": 5218.035794758851,
"count": 675837,
"is_parallel": true,
"self": 5218.035794758851
},
"steps_from_proto": {
"total": 1082.8571089957534,
"count": 1351674,
"is_parallel": true,
"self": 225.29184557951044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 857.5652634162429,
"count": 5406696,
"is_parallel": true,
"self": 857.5652634162429
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 27281.861456528466,
"count": 675837,
"self": 103.76326453801084,
"children": {
"process_trajectory": {
"total": 3784.0227601554843,
"count": 675837,
"self": 3780.493271825492,
"children": {
"RLTrainer._checkpoint": {
"total": 3.529488329992546,
"count": 20,
"self": 3.529488329992546
}
}
},
"_update_policy": {
"total": 23394.075431834972,
"count": 481,
"self": 1476.113508322811,
"children": {
"TorchPOCAOptimizer.update": {
"total": 21917.96192351216,
"count": 14439,
"self": 21917.96192351216
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.529976523481309e-07,
"count": 1,
"self": 9.529976523481309e-07
},
"TrainerController._save_models": {
"total": 0.1471008040025481,
"count": 1,
"self": 0.002914914002758451,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14418588999978965,
"count": 1,
"self": 0.14418588999978965
}
}
}
}
}
}
}